A Systematic Review on Medical Image Segmentation using Deep Learning

Rahmani, Mahdiyeh; Kazemi, Ali; Jalili Aziz, Maryam; Najafzadeh, Ebrahim; Farnia, Parastoo; Ahmadian, Alireza

doi:10.24200/sci.2024.61686.7441

A Systematic Review on Medical Image Segmentation using Deep Learning

Articles in Press

Document Type : Article

Authors

¹ - Medical Physics and Biomedical Engineering Department, Faculty of Medicine, Tehran University of Medical Sciences (TUMS), Tehran, Iran - Research Center of Biomedical Technology and Robotics (RCBTR), Advanced Medical Technologies & Equipment Institute (AMTEI), Imam Khomeini Hospital Complex, Tehran University of Medical Sciences (TUMS), Tehran, Iran

² Department of Electronic and Informatics, Vrije Universities Brussel, Brussels, Belgium, IMEC, Kapeldreef 75, 3001 Leuven, Belgium

³ Department of Medical Physics, School of Medicine, Iran University of Medical Sciences (IUMS), Tehran, Iran

10.24200/sci.2024.61686.7441

Abstract

Medical image segmentation is an essential step in various diagnostic and treatment procedures. This study aimed to conduct a systematic review of state-of-the-art segmentation methods based on the target. The target complexity is a considerable challenge in medical image segmentation and the first issue that experts confront in diagnosing or treating patients. Additionally, each group of targets has similar characteristics, motivating to provide a target-based review to compare the deep-learning (DL)-based studies. This is the first time that a target-based review of medical image segmentation has provided a focus on recent DL developments. This study categorized publications into three targets: tumors, vessels, and pathological. Using a PRISMA strategy while considering the inclusion and exclusion criteria, 118 articles were identified on Google Scholar and PubMed from 2015 to 2023 in the fields of brain, liver, and lung tumors, blood vessels, and pathology image segmentation. This review could assist researchers in selecting the proper network and being aware of possible challenges. We also concluded that medical image segmentation using DL as a cross-disciplinary field is involved with both complex medical data and technical issues. Consequently, new interpretable approaches may be able to bridge the gap between medical specialists and artificial intelligence researchers.

Keywords